The goal of the present study was to develop and evaluate machine learning algorithms for the prediction of blood transfusion donation. The machine learning algorithms studied included multilayer perceptrons (MLPs) and support vector machines (SVMs). The methods were evaluated retrospectively in a group of 600 patients and validated prospectively in a group of 148 patients. We reach a sensitivity of 65.8% and a specificity of 78.2% in the prospective group. This discrimination is very interesting because it could allow to propose to the patients, classified as non-donators, to give their blood in the future. Furthermore, the blood transfusion donation VCI corpus used, has been processed in a different manner than the initial marketing one. Therefore, this recent corpus could give a new training set for testing and improving machine learning methods in the future.
In this article, we present our investigations on the radiation of the power-line communication (PLC) system. Power line communication or power line carrier is a technology for carrying data on a conductor usually dedicated to electric power transmission. At high frequency, the power lines, whose are dimensioned and adjusted for electrical energy transfer, not to carry high frequency (HF) data signal, act then as radiating antennas.The system has a number of issues. The primary one is that power lines are inherently subject to a very noisy common mode current. The proliferation of electric, electronic, mobile and wireless devices contribute to increase this noise. The second major issue is the impact of data communication, the range of used frequencies is expected to be between 1 and 30 MHz. Power lines are unshielded and will act as transmitting antennas for the carried digital signals, and as receiving antennas of surrounded radio communications. Unshielded power cables at higher frequencies represent electromagnetic interferences (EMI) sources for existing communication systems that use the same frequency spectrum, such as military communications, hospital communications, radio astronomy, airport navigation systems and radio amateurs.In the sense of new perspective and growing technology, one of the most important aspects pertaining to the environmental electromagnetic compatibility (EMC) is electronic devices safety and human exposure to the radiation of power lines at high frequencies and possible adverse heat effects.The main objective of this paper is to determine rigorously the radiated electromagnetic field for different antenna lengths, different frequencies or wavelengths on near, intermediate and far zones.According to this 3D EMI distribution and to the real geometry of PLC, we propose a practical approach to minimize the radiated power by controlling the frequency band of the PLC system.
The development of new broadband services over the telephone network requires a good quality of the installation.An important parameter that verifies the quality of a telephone installation system is the symmetry of the line. A measure of the symmetry, made from the telephone exchange center, does not allow remote observation of asymmetry on the client telephone installation.To address this problem, a new method for analyzing the quality of the pair is proposed in this paper. This method consists of evaluating the symmetry of the line by a LF (low frequency) measure made from the telephone exchange side.The aim of this study is to verify the feasibility and the validity of this technique, by a theoretical approach. We have developed a simulation code based on the theory of multi-wire transmission lines, associated with a topological approach. The model and the code are validated using experimental measurements.In the following, we exploit the simulation tool to evaluate this new measurement technique.A second axis of the study was to search for a correlation between the values of LF symmetry evaluated from the telephone exchange side and the values of HF symmetry evaluated at client side.Keywords. quality of a telephone system, symmetry of the cable, multi-wire transmission lines, Defects, ADSL
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.